Can you please tell me how to highlight specific word in the 开发者_C百科HTML
page using JSOUP
? Please I want it to be in JSOUP
because I try to use JQuery
and it causes me a lot of problem
This is my first attempt
Elements elements=doc.getAllElements();
for (Element el:elements)
{
if (el.hasText())
{
int pos = el.text().toUpperCase().indexOf("Hello".toUpperCase());
if (pos >= 0)
{
out.println(pos); // it was disappointed it gives me incorrect position
Element elspc = el.select("*:contains(Hello)").first();
out.println(elspc);
Element span = doc.createElement("span");
span.attr("class", "highlight");
String[] str = el.text().split("\\s");
Here is a class that I built which matches a regex and highlights it using JSOUP as parser. It is probably not the most optimal way of doing it. But it works.
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Highlighter {
private String regex;
private String htmlContent;
Pattern pat;
Matcher mat;
public Highlighter(String searchString, String htmlString) {
regex = buildRegexFromQuery(searchString);
htmlContent = htmlString;
pat = Pattern.compile(regex, Pattern.CASE_INSENSITIVE);
}
public String getHighlightedHtml() {
Document doc = Jsoup.parse(htmlContent);
final List<TextNode> nodesToChange = new ArrayList<TextNode>();
NodeTraversor nd = new NodeTraversor(new NodeVisitor() {
@Override
public void tail(Node node, int depth) {
if (node instanceof TextNode) {
TextNode textNode = (TextNode) node;
String text = textNode.getWholeText();
mat = pat.matcher(text);
if(mat.find()) {
nodesToChange.add(textNode);
}
}
}
@Override
public void head(Node node, int depth) {
}
});
nd.traverse(doc.body());
for (TextNode textNode : nodesToChange) {
Node newNode = buildElementForText(textNode);
textNode.replaceWith(newNode);
}
return doc.toString();
}
private static String buildRegexFromQuery(String queryString) {
String regex = "";
String queryToConvert = queryString;
/* Clean up query */
queryToConvert = queryToConvert.replaceAll("[\\p{Punct}]*", " ");
queryToConvert = queryToConvert.replaceAll("[\\s]*", " ");
String[] regexArray = queryString.split(" ");
regex = "(";
for(int i = 0; i < regexArray.length - 1; i++) {
String item = regexArray[i];
regex += "(\\b)" + item + "(\\b)|";
}
regex += "(\\b)" + regexArray[regexArray.length - 1] + "[a-zA-Z0-9]*?(\\b))";
return regex;
}
private Node buildElementForText(TextNode textNode) {
String text = textNode.getWholeText().trim();
ArrayList<MatchedWord> matchedWordSet = new ArrayList<MatchedWord>();
mat = pat.matcher(text);
while(mat.find()) {
matchedWordSet.add(new MatchedWord(mat.start(), mat.end()));
}
StringBuffer newText = new StringBuffer(text);
for(int i = matchedWordSet.size() - 1; i >= 0; i-- ) {
String wordToReplace = newText.substring(matchedWordSet.get(i).start, matchedWordSet.get(i).end);
wordToReplace = "<b>" + wordToReplace+ "</b>";
newText = newText.replace(matchedWordSet.get(i).start, matchedWordSet.get(i).end, wordToReplace);
}
return new DataNode(newText.toString(), textNode.baseUri());
}
class MatchedWord {
public int start;
public int end;
public MatchedWord(int start, int end) {
this.start = start;
this.end = end;
}
}
}
Just add this in your project. And call
String htmlString = <your html content in string>
Highlighter hl = new Highlighter("hello", htmlString);
String newhtmlString = hl.getHighlightedHtml();
精彩评论